[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124417-en":3,"doc-seo-124417-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},124417,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Achieving interpretable machine learning by functional decomposition of black-box models into explainable predictor effects","Machine learning models often achieve high prediction accuracy using complex black-box architectures, which makes them hard to interpret and limits their adoption in domains such as medicine, ecology, and insurance where transparency, acceptance, and fairness are essential. The work introduces a functional decomposition approach that replaces a prediction function with a surrogate model built from simpler subfunctions, revealing feature contribution directions, strengths, and interaction structure. It is based on “stacked orthogonality,” computed via neural additive modeling and efficient post-hoc orthogonalization, mitigating extrapolation issues and hidden feature interactions.","arXiv :2407 . 18650v1 [ stat .ML] 26 Jul 2024  \nAchieving interpretable machine learning by functional decomposition of black-box models into explainable predictor effects  \nDavid K¨ohler 1 David R¨ugamer2 ,3 Matthias Schmid 1  \n1 Institute for Medical Biometry, Informatics and Epidemiology, University of Bonn, Venusberg-Campus 1, D-53127 Bonn, Germany  \n2 Department of Statistics, LMU Munich, Ludwigstrasse 33,  \nD-80539 Munich, Germany  \n3 Munich Center for Machine Learning, Geschwister-Scholl-Platz 1, D-80539 Munich, Germany  \nAbstract  \nMachine learning (ML) has seen significant growth in both popularity and importance. The high prediction accuracy of ML models is often achieved through complex black-box architectures that are difficult to interpret. This interpretability problem has been hindering the use of ML in fields like medicine, ecology and insurance, where an understanding of the model‘s inner workings is paramount to ensure user acceptance and fairness. The need for interpretable ML models has boosted research in the field of interpretable machine learning (IML) . Here we propose a novel approach for the functional decomposition of black-box predictions, which is considered a core concept of IML. The idea of our method is to replace the prediction function by a surrogate model consisting of simpler subfunctions. Similar to additive regression models, these functions provide insights into the direction and strength of the main feature contributions and their interactions. Our method is based on a novel concept termed “stacked orthogonality“, which ensures that the main effects capture as much functional behavior as possible and do not contain information explained by higher-order interactions. Unlike earlier functional IML approaches, it is neither affected by extrapolation nor by hidden feature interactions. To compute the subfunctions, we propose an algorithm based on neural additive modeling and an efficient post-hoc orthogonalization procedure.  \nKeywords: Functional decomposition | Interpretable machine learning | Neural additive model | Orthogonality  \n1 Introduction  \nMachine learning (ML) has increased greatly in both popularity and significance, driven by an increase in methods, computing power and data availability [33] . On July 5, 2024, a search on Web of Science for publications including the term “machine learning” yielded more than 350,000 results, corresponding to an average annual increase by more than 20% since 2006 . ML models are often characterized by their high generalizability, making them particularly successful when used for supervised learning tasks like classification and risk prediction. In recent years, ML models based on deep artificial neural networks (ANNs) have led to groundbreaking results in the development of high-performing prediction models.  \nThe high prediction accuracy of modern ML models is usually achieved by optimizing complex “black-box” architectures with thousands of parameters. As a consequence, they often result in predictions that are difficult, if not impossible, to interpret. This interpretability problem has been hindering the use of ML in fields like medicine, ecology and insurance, where an understanding of the model and its inner workings is paramount to ensure user acceptance and fairness. In a recent environmental study, for example, we explored the use of ML to derive predictions of stream biological condition in the Chesapeake Bay watershed of the mid-Atlantic coast of North America [26] . Clearly, if these predictions are intended to inform future management policies (projecting, e.g., changes in land use, climate and watershed characteristics), they are required to be interpretable in terms of relevant features as well as the directions and strengths of the feature effects.  \nInterpretable machine learning  \nIn recent years, the need for interpretable ML models has boosted research in the field of interpretable machine learning (IML, [28, 29]) . In this ","cbCaivGVSSAfTT4Q","https://ap.wps.com/l/cbCaivGVSSAfTT4Q","pdf",25918289,1,27,"English","en",105,"# Abstract\n# Introduction\n## Interpretable machine learning","[{\"question\":\"Why is interpretability important in machine learning?\",\"answer\":\"High-performing black-box models can be difficult to interpret, which hinders use in fields like medicine, ecology, and insurance where understanding decision drivers is needed to support acceptance and fairness.\"},{\"question\":\"What is the core idea of the proposed method?\",\"answer\":\"The approach decomposes black-box predictions by replacing the original prediction function with a surrogate model composed of simpler subfunctions that summarize main feature effects and interactions.\"},{\"question\":\"How does “stacked orthogonality” help the decomposition?\",\"answer\":\"It encourages main effects to capture as much functional behavior as possible while preventing them from containing information attributable to higher-order interactions, improving interpretability consistency.\"}]","Achieving interpretable machine learning by functional decomposition of black-box models into explainable predictor effects | PDF",1785822153,68,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"achieving-interpretable-machine-learning-by-functional-decomposition-of-black-box-models-into-explainable-predictor-effects","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/achieving-interpretable-machine-learning-by-functional-decomposition-of-black-box-models-into-explainable-predictor-effects/124417/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is interpretability important in machine learning?","Question",{"text":75,"@type":76},"High-performing black-box models can be difficult to interpret, which hinders use in fields like medicine, ecology, and insurance where understanding decision drivers is needed to support acceptance and fairness.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the core idea of the proposed method?",{"text":80,"@type":76},"The approach decomposes black-box predictions by replacing the original prediction function with a surrogate model composed of simpler subfunctions that summarize main feature effects and interactions.",{"name":82,"@type":73,"acceptedAnswer":83},"How does “stacked orthogonality” help the decomposition?",{"text":84,"@type":76},"It encourages main effects to capture as much functional behavior as possible while preventing them from containing information attributable to higher-order interactions, improving interpretability consistency.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]